dev: Experiment with Agent perfomance agains tasks with attached txt files 6114e5e santiagoahl commited on Jun 10, 2025
feat: Create Experimentation Workflow to Track and validate Agent performance a266a9c santiagoahl commited on Jun 8, 2025
feat: Create Experimentation Workflow to Track and validate Agent performance c3508c9 santiagoahl commited on Jun 8, 2025
achieved a 17% of avg score (GAIA), integrated search and code tools 8dc334e santiagoahl commited on May 18, 2025